Benchmark Almanac

UA-Bench

Qwen2.5-Omni-7B 13.1% leads since August 2026
Not in model cards

Models identify underwater sound sources and their subclasses from audio recordings. The authors repeat the test with silent audio to check reliance on sound.

Made by
Zhe Sun and colleagues
Released
August 2026
Kind
Audio understanding and voice
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Audio → Text
Interaction
Multi-turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Audio and speech
Last model added
June 2026
Scores refreshed
November 20th, 2026
9
Entries in its paper, 5 models we track

Qwen2.5-Omni-7B leads with 13.1% among models released by June 2026 Qwen2.5-Omni-7B leads with 13.1% among models released by June 2026

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in June 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Qwen2.5-Omni-7B Strict single-letter decoder, zero-shot 13.1%
  2. 2 MiDashengLM-7B-1021 Strict single-letter decoder, zero-shot 10.3%
  3. 3 Audio-Flamingo-Next Strict single-letter decoder, zero-shot 8.10%
  4. 4 Voxtral Small Strict single-letter decoder, zero-shot 7.70%
  5. 5 Qwen2-Audio-7B-Instruct Strict single-letter decoder, zero-shot 7.30%
  6. 6 Aero-1-Audio Strict single-letter decoder, zero-shot 6.90%
  7. 7 Gemma 4 E2B Strict single-letter decoder, zero-shot 6.50%
  8. 8 Voxtral-Mini-3B-2507 Strict single-letter decoder, zero-shot 6.10%
  9. 9 Gemma 4 12B Strict single-letter decoder, zero-shot 2.00%

Source: The UA-Bench paper

#EntryScoreSettingDateSource
1 Qwen2.5-Omni-7B 13.1% Strict single-letter decoder, zero-shot Mar 2025 Official leaderboard
2 MiDashengLM-7B-1021 10.3% Strict single-letter decoder, zero-shot Official leaderboard
3 Audio-Flamingo-Next 8.10% Strict single-letter decoder, zero-shot Official leaderboard
4 Voxtral Small 7.70% Strict single-letter decoder, zero-shot Jul 2025 Official leaderboard
5 Qwen2-Audio-7B-Instruct 7.30% Strict single-letter decoder, zero-shot Aug 2024 Official leaderboard
6 Aero-1-Audio 6.90% Strict single-letter decoder, zero-shot Official leaderboard
7 Gemma 4 E2B 6.50% Strict single-letter decoder, zero-shot Mar 2026 Official leaderboard
8 Voxtral-Mini-3B-2507 6.10% Strict single-letter decoder, zero-shot Official leaderboard
9 Gemma 4 12B 2.00% Strict single-letter decoder, zero-shot Jun 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Qwen2.5-Omni-7B 13.1% Strict single-letter decoder, zero-shot Mar 2025 Official leaderboard
2 Voxtral Small 7.70% Strict single-letter decoder, zero-shot Jul 2025 Official leaderboard
3 Qwen2-Audio-7B-Instruct 7.30% Strict single-letter decoder, zero-shot Aug 2024 Official leaderboard
4 Gemma 4 E2B 6.50% Strict single-letter decoder, zero-shot Mar 2026 Official leaderboard
5 Gemma 4 12B 2.00% Strict single-letter decoder, zero-shot Jun 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s paper: Detection pulse, Communication waveform and Ship-radiated noise. Each ranks models on one part of the test. Voxtral Small leads 1 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Detection pulse

5 models we track have a score here.

  1. 1 Voxtral Small ↑1 23.2%
  2. 2 Qwen2.5-Omni-7B ↓1 15%
  3. 3 Gemma 4 12B ↑2 4.50%
  4. 4 Gemma 4 E2B 4.30%
  5. 5 Qwen2-Audio-7B-Instruct ↓2 0%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Qwen
Benchmark paper Not tested since Aug 2026

Source: The UA-Bench paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Qwen2.5-Omni-7B Qwen2-Audio-7B-Instruct 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Qwen2.5-Omni-7B

Source: Official UA-Bench leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 5 models we track, plus 4 other entries on its leaderboard.
  • Pass Newest score The newest is from June 2026, for Gemma 4 12B.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 13.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on sunzhe12.github.io: 5 rows for models we track and 4 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check